Click or drag to resize
MicrosoftResearch.Infer.Maths Namespace
Microsoft Research
Infer.NET maths
Classes
  ClassDescription
Public classAllZeroException
Exception type thrown when probability vector = (0,0,0,...,0).
Public classApproximateSparseVector
A one-dimensional vector of double values, optimised for the case where many of the elements share a common value (which need not be zero) within some tolerance.
Public classBFGS
This implementation of BFGS is based on Algorithm 6.1 from Nocedal and Wright (Second edition, 2006).
Public classContinuedFraction
A class for evaluating continued fractions
Public classDenseVector
1-dimensional dense container of double precision data that supports vector operations.
Public classDerivativeChecker
Class used to check analytic derivatives using finite difference approximation
Public classLBFGS
Implements the LBFGS compact Quasi-Newton solver.
Public classLBFGSArray
Implements the LBFGS compact Quasi-Newton solver on an array of Vectors (which may be sparse)
Public classLineSearch
This line search algorithm is algorithm 3.5/3.6 from Nocedal and Wright (Second edition, 2006). It provides a step length that satisfies the strong Wolfe conditions.
Public classLowerTriangularMatrix
Class for lower triangular matrices
Public classLuDecomposition
Class for calculating and doing operations with an LU decomposition
Public classMatrix
Two-dimensional container of doubles.
Public classMatrixMeanVarianceAccumulator
Class for accumulating weighted noisy matrix observations, and computing sample count, mean matrix, and covariance matrix
Public classMatrixSingularException
Exception thrown when a singular matrix is encountered.
Public classMeanVarianceAccumulator
Class for accumulating weighted noisy scalar observations, and computing sample count, mean, and variance
Public classMeanVarianceAccumulator2
Class for accumulating weighted noisy scalar observations, and computing sample count, mean, and variance
Public classMMath
This class provides mathematical constants and special functions, analogous to System.Math. It cannot be instantiated and consists of static members only.
Public classOptimiserIterationEventArgs
Optimiser iteration event
Public classPiecewiseVector
A one-dimensional vector of double values, optimised for the case where many contiguous ranges of elements have the same value.
Public classPositiveDefiniteMatrix
A subclass of Matrix with extra methods appropriate to positive-definite matrices.
Public classPositiveDefiniteMatrixException
Exception thrown when a matrix is not positive definite.
Public classQuadrature
Quadrature nodes and weights
Public classRand
This class provides a source of non-uniform random numbers. It cannot be instantiated and consists of only static functions.
Public classSerializableMatrix
Helper class for serializing Matrices. To serialize a Matrix, first cast it to SerializableMatrix. After deserializing, cast back to Matrix.
Public classSerializableVector
Helper class for serializing Vectors. To serialize a Vector, first cast it to SerializableVector. After deserializing, cast back to Vector.
Public classSparseVector
A one-dimensional vector of double values, optimised for the case where many of the elements share a common value (which need not be zero).
Public classSparsity
Defines sparsity settings for vectors. The sparsity handling has been designed to deal with large dimensional distributions such as Discrete and Dirichlet distributions.
Public classUpperTriangularMatrix
Upper triangular matrix class
Public classVector
Base class for vectors. DenseVector, SparseVector, and ApproximateSparseVector all inherit from this base class.
Public classVectorMeanVarianceAccumulator
Class for accumulating weighted noisy vector observations, and computing sample count, mean vector, and covariance matrix
Structures
  StructureDescription
Public structureConstantVector
A vector which has a constant value between its start and end indices.
Interfaces
  InterfaceDescription
Public interfaceCanSetAllElementsToT
Supports setting all elements to duplicates of the same value
Public interfaceDiffable
Supports calculating the maximum difference between this instance and another object (not necessarily of the same type)
Public interfaceSettableToT
Supports setting an instance to a value
Public interfaceSettableToPowerT
Supports setting an instance to a value raised to a power
Public interfaceSettableToProductT
Supports setting an instance to the product of two values of the same type
Public interfaceSettableToProductT, U
Supports setting an instance to the product of two values of different types
Public interfaceSettableToRatioT
Supports setting an instance to the ratio of two values of the same type
Public interfaceSettableToRatioT, U
Supports setting an instance to the ratio of two values of different types
Public interfaceSettableToWeightedSumT
Supports setting an instance to the weighted sum of two values of the same type
Public interfaceSettableToWeightedSumExactT
Indicates that a distribution can represent weighted sum of distributions of type T exactly.
Delegates
  DelegateDescription
Public delegateFunctionEval
Delegate type for function evaluation
Public delegateIterationEventHandler
Event delegate for handling iteration event
Public delegateLBFGSArrayFunctionEvalArray
Delegate type for function evaluation
Public delegateLineSearchEval
Delegate type for function evaluation
Enumerations
  EnumerationDescription
Public enumerationBFGSConvergenceCriteria
Convergence criteria: - Gradient: |grad F|/sqrt(dimensions) <= eps - Objective: |F(k+1)-F(k)|<=eps*max{|F(k)|,|F(k+1)|,1}
Public enumerationStorageType
The type of storage used in a vector, which is specified as part of the Sparsity class.